Saliency Map-Aided Generative Adversarial Network for RAW to RGB Mapping
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3449-3457
Abstract
RAW files are widely applied in cameras and scanners as storage because they contain original optical data. Different cameras usually process the RAW files using diverse algorithms that are incompatible. To address the issue, we propose a general transformation method for cross-camera RAW to RGB mapping based on Generative Adversarial Network (GAN). Moreover, we propose a saliency map-aided data augmentation technique and the saliency maps are produced by Saliency GAN (SalGAN). Given RAW file as an input, it jointly predicts the RGB image and corresponding saliency map to enhance perceptual quality in the generated image. The proposed architecture is trained on the Zurich RAW2RGB (ZRR) dataset. Experimental results show that our method can generate more clear and visually plausible images than state-of-the-art networks.Keywords
This publication has 15 references indexed in Scilit:
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Colorful Image Colorization2016
- Learning Representations for Automatic Colorization2016
- Let there be color!ACM Transactions on Graphics, 2016
- Deep Residual Learning for Image Recognition2016
- Deep Colorization2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Colorization using optimizationACM Transactions on Graphics, 2004
- Transferring color to greyscale images2002